The Complexity of Decentralized Control of Markov Decision Processes
Daniel S. BernsteinShlomo ZilbersteinNeil ImmermanPublished in: CoRR (2013)
Keyphrases
- markov decision processes
- decentralized control
- state space
- optimal policy
- reinforcement learning
- dynamic programming
- policy iteration
- average cost
- transition matrices
- decision problems
- partially observable
- reinforcement learning algorithms
- action sets
- multiagent systems
- markov decision process
- power system
- collective behavior
- virtual communities
- reward function
- goal oriented
- decision makers
- data mining